Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 58, Issue 8, 0810017(2021)

Research on Three-Dimensional Reconstruction Algorithm of Weak Textured Objects in Indoor Scenes

Qingpeng Zhang and Yu Cao*
Author Affiliations
  • School of Automation, Harbin University of Science and Technology, Harbin, Heilongjiang 150080, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (12)
    Equations (0)
    References (15)
    Cited By (5)
    Tools
    Paper Information
    Topics
    Figures & Tables(12)
    Image to be matched taken by mobile phone

    Fig. 1. Image to be matched taken by mobile phone

    Download full size
    Matching results of different algorithms. (a) Harris algorithm; (b) SIFT algorithm; (c) Harris-SIFT algorithm; (d) our algorithm

    Fig. 2. Matching results of different algorithms. (a) Harris algorithm; (b) SIFT algorithm; (c) Harris-SIFT algorithm; (d) our algorithm

    Download full size
    Experimental images at different l. (a) l=3; (b) l=2; (c) l=1

    Fig. 3. Experimental images at different l. (a) l=3; (b) l=2; (c) l=1

    Download full size
    Structure of the ResNet50

    Fig. 4. Structure of the ResNet50

    Download full size
    Some experimental images

    Fig. 5. Some experimental images

    Download full size
    Sparse three-dimensional point cloud. (a) SFM algorithm; (b) improved SFM algorithm

    Fig. 6. Sparse three-dimensional point cloud. (a) SFM algorithm; (b) improved SFM algorithm

    Download full size
    Dense point cloud of the object. (a) MVS algorithm; (b) our algorithm

    Fig. 7. Dense point cloud of the object. (a) MVS algorithm; (b) our algorithm

    Download full size
    Three-dimensional reconstruction results of the Poisson surface. (a) Original algorithm; (b) improved algorithm

    Fig. 8. Three-dimensional reconstruction results of the Poisson surface. (a) Original algorithm; (b) improved algorithm

    Download full size

    • Table 1. Accuracies and running time of 4 matching algorithms

      View table

      Table 1. Accuracies and running time of 4 matching algorithms

      Matching algorithmHarrisSIFTHarris-SIFTImproved Harris-SIFT
      Left image feature point2057278614901450
      Right image feature point2172280116121597
      Matching point1600821506492
      Matching accuracy /%81.6193.5493.6794.92
      Matching time /s5.0211.643.943.61

    • Table 2. Image parameters at different l

      View table

      Table 2. Image parameters at different l

      lNumber of image matchesMatch time /sNumber of point clouds
      13271994101823
      2245896199745
      3155414265521

    • Table 3. Errors of different algorithms

      View table

      Table 3. Errors of different algorithms

      AlgorithmXRMSEYRELZlog10
      MVS2.2160.1010.075
      Ours1.1230.0810.038

    • Table 4. Three-dimensional reconstruction results of different algorithms

      View table

      Table 4. Three-dimensional reconstruction results of different algorithms

      AlgorithmTime /minPoint cloudSSIM
      SFM+MVS8.212281660.53
      Improve algorithm6.482616170.81
    Tools

    Get Citation

    Copy Citation Text

    Qingpeng Zhang, Yu Cao. Research on Three-Dimensional Reconstruction Algorithm of Weak Textured Objects in Indoor Scenes[J]. Laser & Optoelectronics Progress, 2021, 58(8): 0810017

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: Jul. 30, 2020

    Accepted: Sep. 15, 2020

    Published Online: Apr. 12, 2021

    The Author Email: Cao Yu (cyhit@163.com)

    DOI:10.3788/LOP202158.0810017

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology